© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 24853
    Prev
    Next
    INDEX
    Explanations

    some

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ategor
    -0.09
    ologue
    -0.09
    nw
    -0.08
     niv
    -0.08
    essaging
    -0.08
     escuch
    -0.07
    .sky
    -0.07
    ‌ب
    -0.07
     acol
    -0.07
    utures
    -0.07
    POSITIVE LOGITS
     prowess
    0.09
     보여
    0.09
    成果
    0.08
    .Show
    0.08
    .Visible
    0.08
     બત
    0.08
     모습을
    0.08
     commitment
    0.08
     Commitment
    0.08
    	show
    0.08
    Activations Density 0.149%

    No Known Activations